Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add alexagriffith/agent-skills --skill explainer-animationgit clone --depth 1 https://github.com/alexagriffith/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alexagriffith/agent-skills/explainer-animation)<a href="https://agentmods.dev/skills/alexagriffith/agent-skills/explainer-animation"><img src="https://agentmods.dev/badge/skills/alexagriffith/agent-skills/explainer-animation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alexagriffith/agent-skills/explainer-animation"><img src="https://agentmods.dev/badge/skills/alexagriffith/agent-skills/explainer-animation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00071 | $0.00846 |
| Opus 5.5 | $0.00028 | $0.00338 |
| Sonnet 5.5 | $0.00014 | $0.00169 |
| Haiku 4.5 | $0.00007 | $0.00085 |
Grade A, and why
explainer-animation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explainer Animation Prompt Generator
Produces a paste-ready prompt for Claude Design (or a similar design canvas).
Always follow the style tokens already loaded in the design project.
The prompt owns structure, layout, boxes, motion, and text. Never invent a palette,
never name a design-system project, never specify colors, fonts, or CSS.
Load only what you need
| Task | Read |
|---|---|
| Write a new prompt | this file → references/principles.md → layout.md → pacing.md → text.md → prompt-template.md |
| Fix teaching / empty lesson / vague headers | references/principles.md + references/text.md |
| Fix layout / overlaps / arrows / fills | references/layout.md |
| Fix timing / reveals / interaction | references/pacing.md |
| Fix on-screen wording | references/text.md |
| Review before paste | references/review.md + references/principles.md (+ the prompt file) |
Do not load every reference for a one-line fix.
Absolute: never style
Forbidden in the prompt: color names, hex codes, palettes, fonts, backgrounds, borders, shadows, CSS, or a named design-system / template.
Required instead: match the reference file’s export contract; use the design system already in this project for colors, fonts, and components.
Layout geometry (bands, gaps, box sizing from labels) is formatting — keep it.
Process
- Have an idea — a claim worth teaching (doc, paste, or verbal). Pull claim + stakes
before any geometry (
references/principles.md). - Invoke this skill — it writes a paste-ready Claude Design prompt (structure, layout, motion, on-screen text only — never colors or fonts).
- Paste into Claude Design — project already has your design system / template. Always create a NEW canvas file. Match the reference file’s export contract. Do not export until you say it looks good.
- Iterate on the live render — hope for something that works in under five passes. Not a guarantee. Batch fixes; scrub transitions; keep the tab focused on export.
What ships with it
21 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/01-model-commodity-question.jpg 80 KB
- examples/01-model-commodity-question.mp4 3184 KB
- examples/02-gpu-parallelism.jpg 89 KB
- examples/02-gpu-parallelism.mp4 1843 KB
- examples/03-cert-manager.jpg 72 KB
- examples/03-cert-manager.png 84 KB
- examples/04-cpu-gpu-ratio.jpg 57 KB
- examples/04-cpu-gpu-ratio.mp4 1702 KB
- examples/before-after/after-with-skill.html 3.8 KB
- examples/before-after/after-with-skill.png 52 KB
- examples/before-after/before-pre-skill.html 4.5 KB
- examples/before-after/before-pre-skill.png 601 KB
- examples/before-after/shipped-gpu-parallelism.jpg 79 KB
- examples/before-after/shipped-gpu-parallelism.png 194 KB
- examples/design-system.png 95 KB
- references/layout.md 3.8 KB
- references/pacing.md 2.7 KB
- references/principles.md 4.9 KB
- references/prompt-template.md 16 KB
- references/review.md 1.9 KB
- references/text.md 3.4 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 82 lines · 71 tokens per session scan A 1897a7203a9e
explainer-animation is a skill published in the GitHub repository alexagriffith/agent-skills (1 stars, last pushed 2mo ago), licensed MIT. It adds 71 tokens to every session and 846 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…